Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Looking At Clearml-Serving - Two Questions - 1, What’S The Status Of The Project 2. How Does One Say How A Model Is Loaded And Served Etc? For Example, If I Have A Spacy Ner Model, I Need To Specify Some Custom Code Right?

Looking at clearml-serving - two questions -

1, what’s the status of the project
2. how does one say how a model is loaded and served etc? For example, if i have a spacy ner model, I need to specify some custom code right?

  
  
Posted 3 years ago
Votes Newest

Answers 18


Sure, got it. Will play around with it 🙂

  
  
Posted 3 years ago

So for adding a model for serve with endpoint you can use

clearml-serving triton --endpoint "<your endpoint>" --model-project "<your project>" --model-name "<your model name>"
when the model is getting updated, is should use the new one

  
  
Posted 3 years ago

Hey SuccessfulKoala55 Like I mentioned, I have a spacy ner model that I need to serve for inference.

  
  
Posted 3 years ago

Hi TrickySheep9 , can you provide more info on your specific use-case?

  
  
Posted 3 years ago

And other question is clearml-serving ready for serious use?

Define serious use? KFserving support is in the pipeline, if that helps.
Notice that clearml-serving is basically a control plane for the serving engine, not to neglect the importance of it, the heavy lifting is done by Triton 🙂 (or any other backend we will integrate with, maybe Seldon)

  
  
Posted 3 years ago

Here’s an example error I get trying it out on one of the example models:
Error: Requested Model project=ClearML Examples name=autokeras imdb example with scalars tags=None not found. 'config.pbtxt' could not be inferred. please provide specific config.pbtxt definition.

  
  
Posted 3 years ago

clearml doesn’t do any “magic” in regard to this for tensorflow, pytorch etc right?

No 😞 and if you have an idea on how, that will be great.
Basically the problem is that there is no "standard" way to know which layer is in/out

  
  
Posted 3 years ago

Thanks

  
  
Posted 3 years ago

Just to confirm AgitatedDove14 - clearml doesn’t do any “magic” in regard to this for tensorflow, pytorch etc right?

  
  
Posted 3 years ago

👍

  
  
Posted 3 years ago

Hi TrickySheep9 , is this model register in your clearml app?

  
  
Posted 3 years ago

Yes. It's a pickle file that I have added via OutputModel

  
  
Posted 3 years ago

Ah, just saw from the example that even that is doing the config pbtxt stuff - https://github.com/allegroai/clearml-serving/blob/main/examples/keras/keras_mnist.py#L51

  
  
Posted 3 years ago

But you have to do config.pbtxt stuff right?

  
  
Posted 3 years ago

Found the custom backend aspect of Triton - https://github.com/triton-inference-server/python_backend
Is that the right way?

  
  
Posted 3 years ago

'config.pbtxt' could not be inferred. please provide specific config.pbtxt definition.

This basically means there is no configuration on how to serve the mode, i.e. size/type of lower (input) layer and output layer.
You can wither store the configuration on the creating Task, like is done here:
https://github.com/allegroai/clearml-serving/blob/b5f5d72046f878bd09505606ca1147d93a5df069/examples/keras/keras_mnist.py#L51
Or you can provide it as standalone file when registering the model with clearml-serving, an example for config.pbtxt :
https://github.com/triton-inference-server/server/blob/main/qa/python_models/identity_fp32/config.pbtxt

  
  
Posted 3 years ago

And other question is clearml-serving ready for serious use?

  
  
Posted 3 years ago

AgitatedDove14 - any thoughts on this?

  
  
Posted 3 years ago
1K Views
18 Answers
3 years ago
one year ago
Tags